• Publications
  • Influence
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures, including FCN and DeconvNet. Expand
PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization
This work trains a convolutional neural network to regress the 6-DOF camera pose from a single RGB image in an end-to-end manner with no need of additional engineering or graph optimisation, demonstrating that convnets can be used to solve complicated out of image plane regression problems. Expand
Semantic object classes in video: A high-definition ground truth database
The Cambridge-driving Labeled Video Database (CamVid) is presented as the first collection of videos with object class semantic labels, complete with metadata, and the relevance of the database is evaluated by measuring the performance of an algorithm from each of three distinct domains: multi-class object recognition, pedestrian detection, and label propagation. Expand
Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
A principled approach to multi-task deep learning is proposed which weighs multiple loss functions by considering the homoscedastic uncertainty of each task, allowing us to simultaneously learn various quantities with different units or scales in both classification and regression settings. Expand
Segmentation and Recognition Using Structure from Motion Point Clouds
This work proposes an algorithm for semantic segmentation based on 3D point clouds derived from ego-motion that works well on sparse, noisy point clouds, and unlike existing approaches, does not need appearance-based descriptors. Expand
Semantic texton forests for image categorization and segmentation
The proposed semantic texton forests are ensembles of decision trees that act directly on image pixels, and therefore do not need the expensive computation of filter-bank responses or local descriptors, and give at least a five-fold increase in execution speed. Expand
Discriminative Learning and Recognition of Image Set Classes Using Canonical Correlations
A novel discriminative learning method over sets is proposed for set classification that maximizes the canonical correlations of within-class sets and minimizes thecanon correlations of between- class sets. Expand
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Robust Semantic Pixel-Wise Labelling
The results show that SegNet achieves state-of-the-art performance even without use of additional cues such as depth, video frames or post-processing with CRF models. Expand
Geometric Loss Functions for Camera Pose Regression with Deep Learning
  • Alex Kendall, R. Cipolla
  • Mathematics, Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 27 February 2017
A number of novel loss functions for learning camera pose which are based on geometry and scene reprojection error are explored, and it is shown how to automatically learn an optimal weighting to simultaneously regress position and orientation. Expand
Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding
A practical system which is able to predict pixel-wise class labels with a measure of model uncertainty, and shows that modelling uncertainty improves segmentation performance by 2-3% across a number of state of the art architectures such as SegNet, FCN and Dilation Network, with no additional parametrisation. Expand